{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T03:14:10Z","timestamp":1791083650653,"version":"4.1.0"},"reference-count":121,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[1998,1,1]],"date-time":"1998-01-01T00:00:00Z","timestamp":883612800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[1998]]},"DOI":"10.1109\/5.726791","type":"journal-article","created":{"date-parts":[[2002,8,24]],"date-time":"2002-08-24T16:26:37Z","timestamp":1030206397000},"page":"2278-2324","source":"Crossref","is-referenced-by-count":48170,"title":["Gradient-based learning applied to document recognition"],"prefix":"10.1109","volume":"86","author":[{"given":"Y.","family":"Lecun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L.","family":"Bottou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Y.","family":"Bengio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P.","family":"Haffner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/72.554195"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.6.1289"},{"key":"ref33","author":"mozer","year":"1991","journal-title":"The perception of multiple objects A connectionist approach"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(82)90024-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/BF00342633"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1962.sp006837"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298793"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1993.5.3.419"},{"key":"ref35","article-title":"Handwritten digit recognition with a back-propagation network","author":"lecun","year":"1990","journal-title":"Advances in Neural Information Processing Systems 2 (NIPS'89)"},{"key":"ref34","author":"lecun","year":"1989","journal-title":"Connectionism in Perspective"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref27","volume":"4","author":"matan","year":"1992","journal-title":"Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-3210-1","author":"bourland","year":"1994","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref20","author":"lecun","year":"1987","journal-title":"Mod\ufffdles Connexionnistes de l'Apprentissage (Connectionist Learning Models)"},{"key":"ref22","volume":"3","author":"bottou","year":"1991","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"21","article-title":"A theoretical framework for back-propagation","author":"lecun","year":"1988","journal-title":"Proc 1988 Connectionist Models Summer School"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.156474"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/5.156477"},{"key":"ref101","first-page":"269","article-title":"Finite-state transducers in language and speech processing","volume":"23","author":"mohri","year":"1997","journal-title":"Computational Linguistics"},{"key":"ref26","first-page":"557","volume":"3","author":"keeler","year":"1991","journal-title":"Neural Information Processing Systems"},{"key":"ref100","author":"pereira","year":"1997","journal-title":"Finite State Devices for Natural Language Processing"},{"key":"ref25","first-page":"41","article-title":"Handwritten digit recognition: Applications of neural net chips and automatic learning","volume":"37","author":"lecun","year":"1989","journal-title":"IEEE Trans Commun"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/78.175747"},{"key":"ref51","first-page":"53","article-title":"Comparison of learning algorithms for handwritten digit recognition","author":"lecun","year":"1995","journal-title":"Int Conf Artificial Neural Networks"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116037"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.6.888"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref56","first-page":"302","volume":"8","author":"saad","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.3.440"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1978.1675179"},{"key":"ref53","first-page":"161","article-title":"Construction of quadratic polynomial classifiers","author":"ott","year":"1976","journal-title":"Proc IEEE Int Conf Pattern Recognition"},{"key":"ref52","first-page":"127","article-title":"Comparing different neural net architectures for classifying handwritten digits","volume":"ii","author":"guyon","year":"1989","journal-title":"Proc IEEE IJCNN"},{"key":"ref40","author":"lang","year":"1988","journal-title":"A time-delay neural-network architecture for speech recognition"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.5.851"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.45.6056"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0"},{"key":"ref5","first-page":"327","author":"cortes","year":"1994","journal-title":"Advances in Neural Information Processing Systems 6"},{"key":"ref8","author":"press","year":"1986","journal-title":"Numerical Recipes The Art of Scientific Computing"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0885-2308(87)90010-6"},{"key":"ref7","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/PGEC.1967.264666"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.66.2396"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1986.1169179"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1613\/jair.105","article-title":"Solving multiclass learning problems via error-correcting output codes","volume":"2","author":"dietterich","year":"1995","journal-title":"J Artificial Intell Res"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90028-J"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/29.21701"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(91)90081-F"},{"key":"ref43","article-title":"Time-delay neural networks embedding time alignment: A performance analysis","author":"haffner","year":"0","journal-title":"Proc Eurospeech 91 2nd European Conf Speech Communication and Technology"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(90)90049-F"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1989.266355"},{"key":"ref71","first-page":"417","article-title":"Neural-net classifiers useful for speech recognition","author":"lippmann","year":"1987","journal-title":"Proc IEEE 1st Int Conf Neural Networks"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"ref76","first-page":"815","article-title":"MLP, LVQ and DP: Comparison &#38; cooperation","volume":"2","author":"driancourt","year":"1991","journal-title":"Proc Int Joint Conf Neural Networks"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/72.125866"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115733"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.115724"},{"key":"ref78","first-page":"579","volume":"4","author":"haffner","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref60","first-page":"42","author":"drucker","year":"1993","journal-title":"Advances in Neural Information Processing Systems 5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/130385.130401"},{"key":"ref61","volume":"5","author":"simard","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref63","author":"burges","year":"1997","journal-title":"Advances in Neural Information Processing Systems 9"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/72.129422"},{"key":"ref65","author":"bridle","year":"1989","journal-title":"Neurocomputing Algorithms Architectures and Applications"},{"key":"ref66","first-page":"151","article-title":"Reading checks with graph transformer networks","volume":"1","author":"lecun","year":"1997","journal-title":"Proc IEEE Int Conf Acoustics Speech Signal Processing"},{"key":"ref67","author":"bengio","year":"1996","journal-title":"Neural Networks for Speech and Sequence Recognition"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.227175"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1994.576889"},{"key":"ref1","author":"duda","year":"1973","journal-title":"Pattern Classification and Scene Analysis"},{"key":"ref109","first-page":"328","article-title":"An EM algorithm for asynchronous input\/output hidden Markov models","author":"bengio","year":"1996","journal-title":"Proc Int Conf Neural Information Processing"},{"key":"ref95","first-page":"901","volume":"7","author":"nowlan","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref108","article-title":"Discriminative feature and model design for automatic speech recognition","author":"rahim","year":"0","journal-title":"Proc Eurospeech '97"},{"key":"ref94","first-page":"745","volume":"6","author":"wolf","year":"1994","journal-title":"Advances in neural information processing systems"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/89.568733"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1049\/ip-vis:19941301"},{"key":"ref106","author":"mohri","year":"1997","journal-title":"A Rational Design for a Weighted Finite-State Transducer Library"},{"key":"ref92","doi-asserted-by":"crossref","DOI":"10.1109\/ICPR.1994.576966","article-title":"Word normalization for on-line handwritten word recognition","author":"bengio","year":"1994","journal-title":"Proc IEEE Int Conf Pattern Recognition"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/72.536317"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/2.144441"},{"key":"ref104","first-page":"427","volume":"7","author":"bengio","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/89.260364"},{"key":"ref103","first-page":"131","article-title":"Weighted determinization and minimization for large vocabulary recognition","author":"mohri","year":"0","journal-title":"Proc Eurospeech '97"},{"key":"ref102","author":"guyon","year":"1996","journal-title":"In Handbook of Character Recognition and Document Image Analysis"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389576"},{"key":"ref112","first-page":"705","article-title":"Recognition of cursive script amounts on postal checks","author":"gilloux","year":"1993","journal-title":"Proc Europ Conf Postal Technol"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/34.57669"},{"key":"ref98","first-page":"186","volume":"1","author":"bourlard","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref99","first-page":"175","volume":"4","author":"bengio","year":"1992","journal-title":"Advances in neural information processing systems"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1996.517075"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1997.609310"},{"key":"ref10","author":"tsypkin","year":"1971","journal-title":"Adaptation and Learning in Automatic Systems"},{"key":"ref11","author":"tsypkin","year":"1973","journal-title":"Foundations of the Theory of Learning Systems"},{"key":"ref12","first-page":"335","article-title":"Learning in random nets","author":"minsky","year":"1961","journal-title":"Proc 4th London Symp Information Theory"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_7"},{"key":"ref14","author":"hinton","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition Volume 1 Foundations"},{"key":"ref15","first-page":"318","volume":"i","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.141"},{"key":"ref16","author":"bryson","year":"1969","journal-title":"Applied Optimal Control"},{"key":"ref82","author":"denker","year":"1995","journal-title":"The Mathematics of Induction"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/72.363436"},{"key":"ref17","first-page":"599","article-title":"A learning scheme for asymmetric threshold networks","author":"lecun","year":"1985","journal-title":"Proc of COGNITIVA'85"},{"key":"ref81","first-page":"1929","article-title":"Connectionist speech recognition with a global MMI algorithm","author":"haffner","year":"0","journal-title":"Proc Eurospeech 93 3rd Europ Conf Speech Communication and Technology"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-82657-3_24"},{"key":"ref84","doi-asserted-by":"crossref","first-page":"75","DOI":"10.21437\/Eurospeech.1997-46","article-title":"Disriminative feature and model design for automatic speech recognition","author":"rahim","year":"1997","journal-title":"Proc EUROSPEECH"},{"key":"ref119","first-page":"40","volume":"1","author":"kramer","year":"1988","journal-title":"Advances in neural information processing systems"},{"key":"ref19","author":"parker","year":"1985","journal-title":"Learning-logic"},{"key":"ref83","author":"bottou","year":"1991","journal-title":"Une approche th\ufffdorique de l'Apprentissage Connexionniste Applications \ufffd la reconnaissance de la Parole"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.1995.538133"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1995.598933"},{"key":"ref116","article-title":"On-line handwriting recognition with neural networks: Spatial representation versus temporal representation","author":"lecun","year":"1993","journal-title":"Proceedings of the 6th International Conference on Handwriting and Drawing"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1988.23829"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000340"},{"key":"ref120","author":"moller","year":"1993","journal-title":"\"Efficient Training of Feed-Forward Neural Networks \""},{"key":"ref89","first-page":"723","volume":"5","author":"schenkel","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"ref121","author":"becker","year":"1988","journal-title":"Improving the convergence of back-propagation learning with second-order methods"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319196"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.3115\/1075812.1075870"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/12.210173"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/4.104196"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx4\/5\/15641\/00726791.pdf?arnumber=726791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T11:35:25Z","timestamp":1704454525000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/726791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998]]},"references-count":121,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/5.726791","relation":{},"ISSN":["0018-9219"],"issn-type":[{"value":"0018-9219","type":"print"}],"subject":[],"published":{"date-parts":[[1998]]}}}